A method, system, device and storage medium for screening massive data of a power grid

Abstract

The application discloses a power grid mass data screening method, system, device and storage medium, comprising: acquiring power data in a period, and preprocessing the power data; performing first logical processing on the preprocessing result; and completing data screening according to the first logical processing. The abnormal situation in the power grid can be more accurately identified, and more reliable support is provided for maintenance and management of the power grid.

Description

Technical Field

[0001] This invention relates to the field of power technology, and in particular to a method, system, device, and storage medium for filtering massive amounts of power grid data. Background Technology

[0002] In power systems, grid data is massive, complex, and highly variable. This data includes various types of information, such as anomalies occurring in various stages of power generation, transmission, substation, distribution, consumption, and dispatch, as well as the causes of these anomalies. As the scale of the power grid continues to expand, the amount of data is also constantly increasing, making data processing, management, and anomaly identification more difficult. To effectively address this challenge, the screening and analysis of power grid data is particularly important.

[0003] However, traditional data screening methods are often inefficient and inaccurate, failing to meet the data processing needs of modern power grids. For example, traditional screening methods may rely solely on simple statistical indicators or fixed thresholds, potentially leading to the missed detection or misjudgment of important anomalies. Furthermore, traditional screening methods often lack the capacity for in-depth data analysis and mining, failing to uncover hidden patterns and regularities within the data. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method, system, device and storage medium for filtering massive amounts of power grid data to solve the problem that important abnormal data is easily missed or misjudged in existing data filtering methods.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for filtering massive amounts of power grid data, comprising:

[0009] Acquire power data within a period and preprocess the power data;

[0010] The preprocessing result is subjected to a first logical processing;

[0011] Based on the first logical processing, the data filtering is completed.

[0012] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0013] Preprocessing the power data includes a first preprocessing and a second preprocessing.

[0014] The first preprocessing includes dividing the power data into first power data, second power data, and third power data;

[0015] The second preprocessing includes averaging the historical first power data and setting a first threshold variable, and then performing a secondary classification on the first threshold variable based on the average obtained after processing.

[0016] When the first power data within a period is greater than the sum of the first threshold variable and the mean, the first power data within the period is set as the first power range;

[0017] When the first power data within a period is less than the sum of the first threshold variable and the mean, and greater than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the second power area.

[0018] When the first power data within a period is less than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the third power area.

[0019] The second preprocessing also includes structuring the second power data within the period;

[0020] The second preprocessing also includes creating a tree diagram of the third power data within the period.

[0021] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0022] The first logical process includes,

[0023] When the first power data in the period is the first power area, if the power generation in the first power data in the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, it is determined that the power generation is excessive and the first power data in the period is abnormal.

[0024] If the power generation in the first power data within the period is less than the absolute value of the difference between the second threshold variable and the average value of the power generation in the historical first power data, the first power distribution logic judgment is entered.

[0025] The first power distribution logic judgment includes,

[0026] If the number of devices with overloaded power consumption in the first power data of a cycle is greater than the number of devices with insufficient power consumption, it is considered that the power distribution error caused the abnormality of the first power data of the cycle.

[0027] If the number of devices with overloaded power consumption in the first power data of a cycle is less than the number of devices with power shortage, then manual intervention is required to determine the cause of the anomaly.

[0028] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0029] The first logical process also includes,

[0030] If the first power data within a cycle falls within the second power range, then the first power data within the cycle is considered normal.

[0031] When the first power data in the period is in the third power area, if the power generation in the first power data in the period is less than the absolute value of the difference between the second threshold variable and the mean value of the power generation in the historical first power data, it is determined that insufficient power generation caused the first power data in the period to be abnormal.

[0032] If the power generation in the first power data within the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, then the second power distribution logic judgment is entered.

[0033] The second power distribution logic judgment includes,

[0034] If the number of devices with power shortage in the first power data of a cycle is greater than the number of devices with power overload, it is considered that the power distribution failure caused the abnormality of the first power data of the cycle.

[0035] If any electrical equipment goes offline in the first power data of the cycle, manual intervention is used to determine the cause of the anomaly.

[0036] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0037] The first logical process also includes,

[0038] When there are missing values ​​in the structured processing results of the second power data within the cycle, the importance of the missing values ​​is determined. If the importance of the missing values ​​is less than 3%, the second power data within the cycle is considered to be fault-free.

[0039] If the significance of missing values ​​is higher than 3%, the second power data within the period is considered faulty and data filling is required.

[0040] The importance of the missing values ​​includes,

[0041]

[0042] Where, α i β represents the importance of the i-th electricity customer. jThe weights represent the structured electricity consumption characteristics: β1 represents the weight of electricity consumption, β2 represents the weight of electricity sales, β3 represents the weight of electricity price, β4 represents the weight of electricity sales revenue, β5 represents the weight of electricity bill collection rate, and α represents the weight of electricity consumption characteristics. i β j This indicates the importance of the j-th electricity consumption characteristic of user i, and n represents the number of users.

[0043] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0044] Obtain the number of child nodes, parent nodes, and root nodes in the first tree diagram of the historical third power data;

[0045] At the end of the cycle, obtain the number of child nodes, parent nodes, and root nodes of the second tree diagram built from the third power data within that cycle;

[0046] Compare the number of nodes in the two tree diagrams above in the following order: number of child nodes, number of root nodes, and number of parent nodes.

[0047] If the number of child nodes is inconsistent, the name of the child node is returned, indicating that the missing child node caused the abnormality of the third power data within the period.

[0048] If the number of root nodes is inconsistent, the name of the root node is returned, indicating that the missing root node caused the abnormality of the third power data in the period.

[0049] As a preferred embodiment of the method for filtering massive amounts of power grid data described in this invention, wherein:

[0050] It also includes the fact that the cycle is 24 hours.

[0051] Record the causes of anomalies in chronological order of occurrence and generate a screening report.

[0052] Secondly, the present invention provides a power grid massive data filtering system, comprising:

[0053] The acquisition module acquires power data within a period and preprocesses the power data.

[0054] The processing module performs a first logical processing on the preprocessing result;

[0055] The filtering module completes the data filtering based on the first logic processing.

[0056] Thirdly, the present invention provides a computing device, comprising:

[0057] Memory, used to store programs;

[0058] A processor for executing the computer-executable instructions, which, when executed by the processor, implement the steps of the method for filtering massive amounts of power grid data.

[0059] Fourthly, the present invention provides a computer-readable storage medium, comprising the steps of implementing the method for filtering massive amounts of power grid data when the program is executed by a processor.

[0060] The beneficial effects of this invention are as follows: It acquires power data within a given period, preprocesses the power data, performs a first logical processing on the preprocessed result, and completes data filtering based on the first logical processing. By preprocessing and classifying massive amounts of power grid data, it achieves refined management of power data, improving the operational efficiency and stability of the power grid. Simultaneously, by establishing a tree diagram and comparing the number of nodes and detecting anomalies, it can more accurately identify abnormal situations in the power grid, providing more reliable support for power grid maintenance and management. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0062] Figure 1 This is a basic flowchart illustrating a method for filtering massive amounts of power grid data according to an embodiment of the present invention.

[0063] Figure 2 A tree diagram illustrating a method for filtering massive amounts of power grid data according to an embodiment of the present invention; Detailed Implementation

[0064] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0065] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0067] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0068] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0069] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0070] Example 1

[0071] Referring to the figure, an embodiment of the present invention provides a method for filtering massive amounts of power grid data, such as... Figure 1 As shown, it includes the following steps:

[0072] S1: Acquire power data within the period and preprocess the power data;

[0073] Furthermore, the preprocessing of the power data includes a first preprocessing and a second preprocessing.

[0074] The first preprocessing includes dividing the power data into first power data, second power data, and third power data;

[0075] The second preprocessing includes averaging the historical first power data and setting a first threshold variable, and then performing a secondary classification on the first threshold variable based on the average obtained after processing.

[0076] When the first power data within a period is greater than the sum of the first threshold variable and the mean, the first power data within the period is set as the first power range;

[0077] When the first power data within a period is less than the sum of the first threshold variable and the mean, and greater than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the second power area.

[0078] When the first power data within a period is less than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the third power area.

[0079] The second preprocessing also includes structuring the second power data within the period;

[0080] The second preprocessing also includes creating a tree diagram of the third power data within the period.

[0081] In the embodiments of this application, the first threshold is 10%-20% of the average value after averaging the historical first power data; although the first threshold does not take other values, other values ​​for the same purpose should be within the protection scope of this application.

[0082] It should be noted that the beneficial effects of structuring the second power data within the cycle are mainly reflected in the following aspects:

[0083] Improved data readability: Structured processing makes power data more readable throughout the cycle, facilitating analysis and understanding.

[0084] Improved data processing efficiency: Through structured processing, power data can be stored and retrieved more efficiently during the processing, thereby improving data processing efficiency.

[0085] Improved data accuracy: Structured processing helps reduce noise and redundant information in data, thereby improving data accuracy.

[0086] Enhanced data security: Structured processing helps protect the privacy and security of power data, and enhances data security through technologies such as data anonymization and encryption.

[0087] Data quality improvement: Through structured processing, the quality of power data can be improved, including data integrity, accuracy, and consistency.

[0088] Enhanced decision support capabilities: Structured power data can provide decision-makers with more accurate and timely data support, which helps improve the efficiency and accuracy of decision-making.

[0089] Increased automation: Structured processing makes power data easier for machines to understand and process, thereby helping to improve automation and reduce human intervention.

[0090] It should be noted that the beneficial effects of establishing a tree diagram for the third-generation power data within the cycle are mainly reflected in the following aspects:

[0091] Data visualization: Tree diagrams are an intuitive data visualization tool that can present complex relationships in power data in an easy-to-understand way, helping to analyze and understand the data.

[0092] Clear data structure: Tree diagrams can clearly show the hierarchical structure and classification of power data, which helps to discover patterns and regularities in the data.

[0093] Clear data relationships: Tree diagrams can clearly represent the parent-child and hierarchical relationships between power data, which helps to understand the associations and dependencies between data.

[0094] Convenient data comparison: Tree diagrams facilitate data comparison, such as comparing electricity data of different categories or time periods, which helps to discover differences and changes in the data.

[0095] Accurate data prediction: By establishing a tree model, electricity data can be predicted and analyzed, thereby better predicting future electricity demand and supply.

[0096] Data-driven decision support: Tree diagrams can provide decision-makers with clear data support, helping them make more accurate and informed decisions.

[0097] Highly interactive: Tree diagrams can be operated and displayed in an interactive way, such as by clicking or dragging nodes to view data at different levels, improving the convenience and efficiency of data interaction.

[0098] S2: Perform the first logical processing on the preprocessing result;

[0099] The first logical processing includes,

[0100] When the first power data in the period is the first power area, if the power generation in the first power data in the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, it is determined that the power generation is excessive and the first power data in the period is abnormal.

[0101] If the power generation in the first power data within the period is less than the absolute value of the difference between the second threshold variable and the average value of the power generation in the historical first power data, the first power distribution logic judgment is entered.

[0102] In the embodiments of this application, the second threshold is 5%-15% of the average value of the power generation in the first power data within the historical period after averaging. Although the second threshold does not take other values, other values ​​for the same purpose should be within the protection scope of this application.

[0103] The first power distribution logic judgment includes,

[0104] If the number of devices with overloaded power consumption in the first power data of a cycle is greater than the number of devices with insufficient power consumption, it is considered that the power distribution error caused the abnormality of the first power data of the cycle.

[0105] If the number of devices with overloaded power consumption in the first power data of a cycle is less than the number of devices with power shortage, then manual intervention is required to determine the cause of the anomaly.

[0106] Furthermore, the first logical process also includes,

[0107] If the first power data within a cycle falls within the second power range, then the first power data within the cycle is considered normal.

[0108] When the first power data in the period is in the third power area, if the power generation in the first power data in the period is less than the absolute value of the difference between the second threshold variable and the mean value of the power generation in the historical first power data, it is determined that insufficient power generation caused the first power data in the period to be abnormal.

[0109] If the power generation in the first power data within the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, then the second power distribution logic judgment is entered.

[0110] The second power distribution logic judgment includes,

[0111] If the number of devices with power shortage in the first power data of a cycle is greater than the number of devices with power overload, it is considered that the power distribution failure caused the abnormality of the first power data of the cycle.

[0112] If any electrical equipment goes offline in the first power data of the cycle, manual intervention is used to determine the cause of the anomaly.

[0113] Furthermore, the first logical processing also includes,

[0114] When there are missing values ​​in the structured processing results of the second power data within the cycle, the importance of the missing values ​​is determined. If the importance of the missing values ​​is less than 3%, the second power data within the cycle is considered to be fault-free.

[0115] If the significance of missing values ​​is higher than 3%, the second power data within the period is considered faulty and data filling is required.

[0116] The importance of missing values ​​includes,

[0117]

[0118] Where, α i β represents the importance of the i-th electricity customer. j The weights represent the structured electricity consumption characteristics: β1 represents the weight of electricity consumption, β2 represents the weight of electricity sales, β3 represents the weight of electricity price, β4 represents the weight of electricity sales revenue, β5 represents the weight of electricity bill collection rate, and α represents the weight of electricity consumption characteristics. i β j This indicates the importance of the j-th electricity consumption characteristic of user i, and n represents the number of users.

[0119] Obtain the number of child nodes, parent nodes, and root nodes in the first tree diagram of the historical third power data;

[0120] At the end of the cycle, obtain the number of child nodes, parent nodes, and root nodes of the second tree diagram built from the third power data within that cycle;

[0121] Compare the number of nodes in the two tree diagrams above in the following order: number of child nodes, number of root nodes, and number of parent nodes.

[0122] If the number of child nodes is inconsistent, the name of the child node is returned, indicating that the missing child node caused the abnormality of the third power data within the period.

[0123] If the number of root nodes is inconsistent, the name of the root node is returned, indicating that the missing root node caused the abnormality of the third power data in the period.

[0124] In the embodiments of this application, the first power data is power grid operation and equipment detection or monitoring data; the second power data is power grid marketing data; and the third power data is power grid management data.

[0125] In the embodiments of this application, the parent node is the third power data;

[0126] The sub-nodes are collaborative office data, human resources data, financial management data, procurement and supply chain data, production management data, sales and marketing data, energy management data, and equipment management data;

[0127] The root node of the collaborative office data includes data related to office processes such as emails, document management, meeting minutes, and task assignments.

[0128] The root node of the human resources data includes human resources-related data such as employee personal information, recruitment records, employee training, and performance evaluation.

[0129] The root node of the sub-node financial management data includes financial statements, cost analysis, budget execution and other data related to financial management.

[0130] The root node for procurement and supply chain data includes supplier information, purchase orders, inventory management, and other data related to procurement and supply chain.

[0131] The root node of the child node production management data includes production planning, production progress, quality control and other production management-related data.

[0132] The root node for child node sales and marketing data includes sales orders, customer information, market research, and other sales and marketing-related data.

[0133] The root node of the energy management data includes data related to energy management, such as energy consumption, energy-saving measures, and energy efficiency.

[0134] The root node of the child node device management data includes data related to device management, such as device maintenance, fault handling, and device efficiency. S3: Based on the first logic processing, complete the data filtering.

[0135] Furthermore, the cycle is 24 hours.

[0136] Record the causes of anomalies in chronological order of occurrence and generate a screening report.

[0137] This embodiment also provides a power grid massive data filtering system, including:

[0138] The acquisition module acquires power data within a period and preprocesses the power data.

[0139] The processing module performs a first logical processing on the preprocessing result;

[0140] The filtering module completes the data filtering based on the first logic processing.

[0141] Furthermore, this also includes:

[0142] Memory, used to store programs;

[0143] A processor for loading the program to execute the method for filtering massive amounts of power grid data.

[0144] This embodiment also provides a computer-readable storage medium storing a program that, when executed by a processor, implements the method for filtering massive amounts of power grid data.

[0145] The storage medium proposed in this embodiment and the method for filtering massive amounts of power grid data proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0146] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0147] Example 2

[0148] Referring to Tables 1-2, an embodiment of the present invention provides a method for filtering massive amounts of power grid data. To verify its beneficial effects, a scientific demonstration is conducted through specific implementation methods and their effects.

[0149] The specific details of this embodiment are as follows:

[0150] Table 1. Structured tabular data obtained from the second power data within a certain period.

[0151]

[0152] In this embodiment of the application, the structured table of the second power data acquisition within the period is shown in Table 1, where the importance of user 1 is 0.1, the importance of user 2 is 0.125, the importance of user 3 is 0.2, the importance of user 4 is 0.173, the importance of user 5 is 0.05, the importance of user 6 is 0.09, the importance of user 7 is 0.11, the importance of user 8 is 0.152, the weight of electricity consumption is 0.1, the weight of electricity sales is 0.2, the weight of electricity price is 0.3, the weight of electricity sales revenue is 0.3, and the weight of electricity bill collection rate is 0.1.

[0153] Based on the formula for the importance of missing values,

[0154]

[0155] Where, α i β represents the importance of the i-th electricity customer. jThe weights represent the structured electricity consumption characteristics: β1 represents the weight of electricity consumption, β2 represents the weight of electricity sales, β3 represents the weight of electricity price, β4 represents the weight of electricity sales revenue, β5 represents the weight of electricity bill collection rate, and α represents the weight of electricity consumption characteristics. i β j This indicates the importance of the j-th electricity consumption characteristic of user i, and n represents the number of users.

[0156] As can be seen, the importance of the missing values ​​in Table 1 is as follows: α3β1 = 2%, α7β2 = 2.2%, α5β4 = 1.5%, and α8β5 = 1.52%. All of the above missing values ​​need to be filled in.

[0157] Table 2. Screening Report

[0158]

[0159] This invention provides a method for filtering massive amounts of power grid data, comprising the following steps:

[0160] 1. Collect massive amounts of data from the power grid, including power data and other related data.

[0161] 2. Preprocess the collected data, including data cleaning, data transformation, and data standardization.

[0162] 3. Divide the preprocessed data into time series to form datasets for multiple periods.

[0163] 4. Perform first threshold classification and second threshold classification on the power data within each period. The first threshold classification includes classifying the mean of the power data, and the second threshold classification includes classifying key indicators such as power generation and power consumption.

[0164] 5. Based on the results of the first threshold classification and the second threshold classification, the power data within the period is divided into a first power area, a second power area, and a third power area.

[0165] 6. Perform structured processing on the first power data within the period, including extracting and integrating indicators such as equipment power consumption characteristics, power consumption, power sales, electricity price, power sales revenue, and electricity bill collection rate.

[0166] 7. Based on the results of the structured processing, establish a tree diagram of the first power data within the period.

[0167] 8. Perform structured processing on the second power data within the cycle, and create a tree diagram for the third power data within the cycle.

[0168] 9. Perform node count comparison and anomaly detection on the tree diagram, including comparison of the number of child nodes, root nodes, and parent nodes.

[0169] 10. Based on the comparison of node counts and the results of anomaly detection, generate a screening report, including information such as the time of anomaly occurrence and the cause of the anomaly.

[0170] In summary, by preprocessing and classifying massive amounts of power grid data, refined management of power data has been achieved, improving the operational efficiency and stability of the power grid. Furthermore, by establishing a tree diagram and comparing the number of nodes and detecting anomalies, abnormal situations in the power grid can be identified more accurately, providing more reliable support for power grid maintenance and management.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for filtering massive amounts of power grid data, characterized in that, include: Acquire power data within a period and preprocess the power data; The preprocessing result is subjected to a first logical processing; Based on the first logical processing, the data filtering is completed; The first logical process includes, When the first power data in the period is the first power area, if the power generation in the first power data in the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, it is determined that the power generation is excessive and the first power data in the period is abnormal. If the power generation in the first power data within the period is less than the absolute value of the difference between the second threshold variable and the average value of the power generation in the historical first power data, the first power distribution logic judgment is entered. The first power distribution logic judgment includes, If the number of devices with overloaded power consumption in the first power data of a cycle is greater than the number of devices with insufficient power consumption, it is considered that the power distribution error caused the abnormality of the first power data of the cycle. If the number of devices with overloaded power consumption in the first power data of the cycle is less than the number of devices with power shortage, then manual intervention is required to determine the cause of the anomaly. The second threshold is 5%-15% of the average of the power generation in the first power data within the historical period. The first logical process also includes, If the first power data within a cycle falls within the second power range, then the first power data within the cycle is considered normal. When the first power data in the period is in the third power area, if the power generation in the first power data in the period is less than the absolute value of the difference between the second threshold variable and the mean value of the power generation in the historical first power data, it is determined that insufficient power generation caused the first power data in the period to be abnormal. If the power generation in the first power data within the period is greater than the sum of the second threshold variable and the average value of the power generation in the historical first power data, then the second power distribution logic judgment is entered. The second power distribution logic judgment includes, If the number of devices with power shortage in the first power data of a cycle is greater than the number of devices with power overload, it is considered that the power distribution failure caused the abnormality of the first power data of the cycle. If any electrical equipment goes offline in the first power data of the cycle, manual intervention will be used to determine the cause of the anomaly. The primary power data consists of power grid operation and equipment testing or monitoring data. The second type of electricity data is grid marketing data, and the third type of electricity data is grid management data.

2. The method for filtering massive amounts of power grid data as described in claim 1, characterized in that: Preprocessing the power data includes a first preprocessing and a second preprocessing. The first preprocessing includes dividing the power data into first power data, second power data, and third power data; The second preprocessing includes averaging the historical first power data and setting a first threshold variable, and then performing a secondary classification on the first threshold variable based on the average obtained after processing. When the first power data within a period is greater than the sum of the first threshold variable and the mean, the first power data within the period is set as the first power range; When the first power data within a period is less than the sum of the first threshold variable and the mean, and greater than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the second power area. When the first power data within a period is less than the absolute value of the difference between the first threshold variable and the mean, the first power data within the period is set as the third power area. The second preprocessing also includes structuring the second power data within the period; The second preprocessing also includes creating a tree diagram of the third power data within the period; The first threshold is 10%-20% of the average value of the historical first power data after averaging.

3. The method for filtering massive amounts of power grid data as described in claim 2, characterized in that: The first logical process also includes, When there are missing values ​​in the structured processing results of the second power data within the cycle, the importance of the missing values ​​is determined. If the importance of the missing values ​​is less than 3%, the second power data within the cycle is considered to be fault-free. If the significance of missing values ​​is higher than 3%, the second power data within the period is considered faulty and data filling is required. The importance of the missing values ​​includes, in, This indicates the importance of the i-th electricity customer. The weights representing the structured electricity consumption characteristics. Indicates the weight of electricity consumption. Indicates the weight of electricity sales volume. Indicates the weight of electricity prices. Indicates the weight of electricity sales revenue. The weights representing the electricity bill collection rate Indicates user The The importance of each electricity consumption characteristic This indicates the number of users.

4. The method for filtering massive amounts of power grid data as described in claim 3, characterized in that: Obtain the number of child nodes, parent nodes, and root nodes in the first tree diagram of the historical third power data; At the end of the cycle, obtain the number of child nodes, parent nodes, and root nodes of the second tree diagram built from the third power data within that cycle; Compare the number of nodes in the two tree diagrams above in the following order: number of child nodes, number of root nodes, and number of parent nodes. If the number of child nodes is inconsistent, the name of the child node is returned, indicating that the missing child node caused the abnormality of the third power data within the period. If the number of root nodes is inconsistent, the name of the root node is returned, indicating that the missing root node caused the abnormality of the third power data in the period.

5. The method for filtering massive amounts of power grid data as described in claim 4, characterized in that: It also includes the fact that the cycle is 24 hours. Record the causes of anomalies in chronological order of occurrence and generate a screening report.

6. A system for filtering massive amounts of power grid data, characterized in that, The method of claim 1 is used, comprising: The acquisition module acquires power data within a period and preprocesses the power data. The processing module performs a first logical processing on the preprocessing result; The filtering module completes the data filtering based on the first logic processing.

7. An electronic device, characterized in that, include: Memory, used to store programs; A processor for loading the program to perform the steps of the method for filtering massive amounts of power grid data as described in any one of claims 1-5.

8. A computer-readable storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the method for filtering massive amounts of power grid data as described in any one of claims 1-5.

Images